MIT一篇cvpr2011实现的快速确定图像边缘的算法，效率比以前快50000多倍！！！MIT的Chang和Fisher基于物体外观的相似
度和相异性给每个分割分配一个总的得分，与其他方法为找到一个最高得分的分割不同，他们用高效的找到许多次优的分割，这样不仅可以找到最优的分割，也能找
到许多它的分割。
GIT的Anthony Yezzi教授评价说”"There are a lot of competing methodologies
out there, so it’s hard for me to say that this is going to
revolutionize segmentation, but, the way in which Chang and Fisher’s
algorithm represents images is “an interesting new vehicle that I think
could get a lot of mileage, even beyond segmentation.”
An algorithm for identifying the boundaries of objects in digital images is 50,000 times more efficient than its predecessor.